Added extra metadata support for chaptered M4B files

CHANGELOG.md

@@ -1,9 +1,11 @@
 # v1.0.8 (pre-release)
 - Added support for AMD GPUs in Linux (Special thanks to @hg000125 for his contribution in #23)
+- Added extra metadata support for chaptered M4B files, ensuring better compatibility with audiobook players.
 - Skipping PyTorch CUDA installation if GPU is not NVIDIA in WINDOWS_INSTALL.bat script, preventing unnecessary installation of PyTorch.
-- Fixed voice preview player keeps open at the background after stopping the preview.
+- Fixed voice preview player keeps playing silently at the background after preview ends.
-- Improved input box background color handling, fixed display issues in Linux Wayland.
+- Improved input box background color handling, fixed display issues in Linux.
 - Better sleep state handling for Linux.
+- Improvements in documentation and code.
 
 # v1.0.7
 - Improve chaptered audio generation by outputting directly as `m4b` instead of converting from `wav`.

abogen/book_handler.py

@@ -1494,8 +1494,13 @@ class HandlerDialog(QDialog):
             authors_text = ", ".join(self.book_metadata["authors"])
             html_content += f"<p style='text-align: center; font-style: italic;'>By {authors_text}</p>"
 
-        if self.book_metadata["publisher"]:
+        if self.book_metadata["publisher"] or self.book_metadata.get("publication_year"):
-            html_content += f"<p style='text-align: center;'>Published by {self.book_metadata['publisher']}</p>"
+            pub_info = []
+            if self.book_metadata["publisher"]:
+                pub_info.append(f"Published by {self.book_metadata['publisher']}")
+            if self.book_metadata.get("publication_year"):
+                pub_info.append(f"Year: {self.book_metadata['publication_year']}")
+            html_content += f"<p style='text-align: center;'>{' | '.join(pub_info)}</p>"
 
         html_content += "<hr/>"
 
@@ -1517,24 +1522,51 @@ class HandlerDialog(QDialog):
             "description": None,
             "cover_image": None,
             "publisher": None,
+            "publication_year": None,
         }
 
         if self.file_type == "epub":
-            title_items = self.book.get_metadata("DC", "title")
+            try:
-            if title_items:
+                title_items = self.book.get_metadata("DC", "title")
-                metadata["title"] = title_items[0][0]
+                if title_items and len(title_items) > 0:
+                    metadata["title"] = title_items[0][0]
+            except Exception as e:
+                logging.warning(f"Error extracting title metadata: {e}")
 
-            author_items = self.book.get_metadata("DC", "creator")
+            try:
-            if author_items:
+                author_items = self.book.get_metadata("DC", "creator")
-                metadata["authors"] = [author[0] for author in author_items]
+                if author_items:
+                    metadata["authors"] = [author[0] for author in author_items if len(author) > 0]
+            except Exception as e:
+                logging.warning(f"Error extracting author metadata: {e}")
 
-            desc_items = self.book.get_metadata("DC", "description")
+            try:
-            if desc_items:
+                desc_items = self.book.get_metadata("DC", "description")
-                metadata["description"] = desc_items[0][0]
+                if desc_items and len(desc_items) > 0:
+                    metadata["description"] = desc_items[0][0]
+            except Exception as e:
+                logging.warning(f"Error extracting description metadata: {e}")
 
-            publisher_items = self.book.get_metadata("DC", "publisher")
+            try:
-            if publisher_items:
+                publisher_items = self.book.get_metadata("DC", "publisher")
-                metadata["publisher"] = publisher_items[0][0]
+                if publisher_items and len(publisher_items) > 0:
+                    metadata["publisher"] = publisher_items[0][0]
+            except Exception as e:
+                logging.warning(f"Error extracting publisher metadata: {e}")
+                
+            # Try to extract publication year
+            try:
+                date_items = self.book.get_metadata("DC", "date")
+                if date_items and len(date_items) > 0:
+                    date_str = date_items[0][0]
+                    # Try to extract just the year from the date string
+                    year_match = re.search(r'\b(19|20)\d{2}\b', date_str)
+                    if year_match:
+                        metadata["publication_year"] = year_match.group(0)
+                    else:
+                        metadata["publication_year"] = date_str
+            except Exception as e:
+                logging.warning(f"Error extracting publication date metadata: {e}")
 
             for item in self.book.get_items_of_type(ebooklib.ITEM_COVER):
                 metadata["cover_image"] = item.get_content()
@@ -1565,6 +1597,18 @@ class HandlerDialog(QDialog):
 
                 metadata["publisher"] = pdf_info.get("creator", None)
                 
+                # Try to extract publication date from PDF metadata
+                if "creationDate" in pdf_info:
+                    date_str = pdf_info["creationDate"]
+                    year_match = re.search(r'D:(\d{4})', date_str)
+                    if year_match:
+                        metadata["publication_year"] = year_match.group(1)
+                elif "modDate" in pdf_info:
+                    date_str = pdf_info["modDate"]
+                    year_match = re.search(r'D:(\d{4})', date_str)
+                    if year_match:
+                        metadata["publication_year"] = year_match.group(1)
+
             if len(self.pdf_doc) > 0:
                 try:
                     pix = self.pdf_doc[0].get_pixmap(matrix=fitz.Matrix(2, 2))
@@ -1580,10 +1624,43 @@ class HandlerDialog(QDialog):
         else:
             return self._get_pdf_selected_text()
 
+    def _format_metadata_tags(self):
+        """Format metadata tags for insertion at the beginning of the text"""
+        import datetime
+        
+        metadata = self.book_metadata
+        filename = os.path.splitext(os.path.basename(self.book_path))[0]
+        current_year = str(datetime.datetime.now().year)
+        
+        # Get values with fallbacks
+        title = metadata.get("title") or filename
+        authors = metadata.get("authors") or ["Unknown"]
+        authors_text = ", ".join(authors)
+        album_artist = authors_text or "Unknown"
+        year = metadata.get("publication_year") or current_year  # Use publication year if available
+        
+        # Count chapters/pages
+        total_chapters = len(self.checked_chapters)
+        chapter_text = f"{total_chapters} {'Chapters' if self.file_type == 'epub' else 'Pages'}"
+        
+        # Format metadata tags
+        metadata_tags = [
+            f"<<METADATA_TITLE:{title}>>",
+            f"<<METADATA_ARTIST:{authors_text}>>",
+            f"<<METADATA_ALBUM:{title} ({chapter_text})>>",
+            f"<<METADATA_YEAR:{year}>>",
+            f"<<METADATA_ALBUM_ARTIST:{album_artist}>>"
+        ]
+        
+        return "\n".join(metadata_tags)
+
     def _get_epub_selected_text(self):
         all_checked_identifiers = set()
         chapter_texts = []
 
+        # Add metadata tags at the beginning
+        metadata_tags = self._format_metadata_tags()
+        
         item_order_counter = 0
         ordered_checked_items = []
 
@@ -1608,7 +1685,7 @@ class HandlerDialog(QDialog):
                 marker = f"<<CHAPTER_MARKER:{title}>>"
                 chapter_texts.append(marker + "\n" + text)
 
-        full_text = "\n\n".join(chapter_texts)
+        full_text = metadata_tags + "\n\n" + "\n\n".join(chapter_texts)
         return full_text, all_checked_identifiers
 
     def _get_pdf_selected_text(self):
@@ -1617,6 +1694,9 @@ class HandlerDialog(QDialog):
         section_titles = []
         all_content = []
 
+        # Add metadata tags at the beginning
+        metadata_tags = self._format_metadata_tags()
+
         pdf_has_no_bookmarks = (
             hasattr(self, "has_pdf_bookmarks") and not self.has_pdf_bookmarks
         )
@@ -1641,7 +1721,7 @@ class HandlerDialog(QDialog):
                     if text:
                         all_content.append(text)
                         included_text_ids.add(page_id)
-            return "\n\n".join(all_content), all_checked_identifiers
+            return metadata_tags + "\n\n" + "\n\n".join(all_content), all_checked_identifiers
 
         iterator = QTreeWidgetItemIterator(self.treeWidget)
         while iterator.value():
@@ -1699,7 +1779,7 @@ class HandlerDialog(QDialog):
                         included_text_ids.add(identifier)
             iterator += 1
 
-        return "\n\n".join([t[1] for t in section_titles]), all_checked_identifiers
+        return metadata_tags + "\n\n" + "\n\n".join([t[1] for t in section_titles]), all_checked_identifiers
 
     def on_save_chapters_changed(self, state):
         self.save_chapters_separately = bool(state)

abogen/conversion.py

@@ -221,6 +221,10 @@ class ConversionThread(QThread):
             # Clean up text using utility function
             text = clean_text(text)
             
+            # Remove metadata markers from the text to be processed
+            metadata_pattern = r"<<METADATA_[^:]+:[^>]*>>"
+            text = re.sub(metadata_pattern, "", text)
+
             # --- Chapter splitting logic ---
             chapter_pattern = r"<<CHAPTER_MARKER:(.*?)>>"
             chapter_splits = list(re.finditer(chapter_pattern, text))
@@ -511,7 +515,7 @@ class ConversionThread(QThread):
                             [
                                 "ffmpeg",
                                 "-y",
-                                "-thread_queue_size", "1024", # Increased thread_queue_size for chapter opus
+                                "-thread_queue_size", "32768", # Increased thread_queue_size for chapter opus
                                 "-f",
                                 "f32le",
                                 "-ar",
@@ -597,7 +601,7 @@ class ConversionThread(QThread):
                     opus_out_path = f"{base_filepath_no_ext}.opus"
                     ffmpeg_cmd_opus = [
                         "ffmpeg", "-y",
-                        "-thread_queue_size", "1024", # Increased thread_queue_size
+                        "-thread_queue_size", "32768", # Increased thread_queue_size
                         "-f", "f32le", "-ar", "24000", "-ac", "1", "-i", "pipe:0",
                         "-c:a", "libopus", "-b:a", "24000", # Original bitrate
                         opus_out_path,
@@ -701,13 +705,20 @@ class ConversionThread(QThread):
             static_ffmpeg.add_paths()
             ffmpeg_cmd = [
                 "ffmpeg", "-y",
-                "-thread_queue_size", "1024", # Increased thread_queue_size
+                "-thread_queue_size", "32768", # Increased thread_queue_size
                 "-f", "f32le", "-ar", "24000", "-ac", "1", "-i", "pipe:0",
                 "-i", chapters_info_path,
                 "-map", "0:a",
                 "-map_metadata", "1", 
                 "-map_chapters", "1",
-                "-c:a", "aac", "-b:a", "128k", # Explicitly AAC with a common bitrate
+                # Add metadata tags
+                "-metadata", "composer=Narrator",
+                "-metadata", "genre=Audiobook",
+                # Extract metadata from text markers if available
+                *self._extract_and_add_metadata_tags_to_ffmpeg_cmd(),
+                "-c:a", "aac",
+                "-q:a", "2", # Quality-based VBR for better quality control (lower = better, range 0.1-2)
+                "-movflags", "+faststart+use_metadata_tags",  # Added for better compatibility
                 output_m4b_path,
             ]
 
@@ -742,6 +753,69 @@ class ConversionThread(QThread):
                 except Exception as e_clean:
                     self.log_updated.emit((f"Warning: Could not delete temporary chapter file {chapters_info_path}: {e_clean}", "orange"))
 
+    def _extract_and_add_metadata_tags_to_ffmpeg_cmd(self):
+        """Extract metadata tags from text content and add them to ffmpeg command"""
+        metadata_options = []
+        
+        # Get the input text (either direct or from file)
+        text = ""
+        if self.is_direct_text:
+            text = self.file_name
+        else:
+            try:
+                encoding = detect_encoding(self.file_name)
+                with open(self.file_name, "r", encoding=encoding, errors="replace") as file:
+                    text = file.read()
+            except Exception as e:
+                self.log_updated.emit(f"Warning: Could not read file for metadata extraction: {e}")
+                return []
+                
+        # Extract metadata tags using regex
+        title_match = re.search(r"<<METADATA_TITLE:([^>]*)>>", text)
+        artist_match = re.search(r"<<METADATA_ARTIST:([^>]*)>>", text) 
+        album_match = re.search(r"<<METADATA_ALBUM:([^>]*)>>", text)
+        year_match = re.search(r"<<METADATA_YEAR:([^>]*)>>", text)
+        album_artist_match = re.search(r"<<METADATA_ALBUM_ARTIST:([^>]*)>>", text)
+        
+        # Use display path or filename as fallback for title
+        filename = os.path.splitext(os.path.basename(self.display_path if self.display_path else self.file_name))[0]
+        
+        # Add title metadata
+        if title_match:
+            metadata_options.extend(["-metadata", f"title=Dinginliğin Gücü"])
+        else:
+            metadata_options.extend(["-metadata", f"title={filename}"])
+            
+        # Add artist metadata
+        if artist_match:
+            metadata_options.extend(["-metadata", f"artist={artist_match.group(1)}"])
+        else:
+            metadata_options.extend(["-metadata", f"artist=Unknown"])
+            
+        # Add album metadata
+        if album_match:
+            metadata_options.extend(["-metadata", f"album={album_match.group(1)}"])
+        else:
+            metadata_options.extend(["-metadata", f"album={filename}"])
+            
+        # Add year metadata
+        if year_match:
+            metadata_options.extend(["-metadata", f"date={year_match.group(1)}"])
+        else:
+            # Use current year if year is not specified
+            import datetime
+            current_year = datetime.datetime.now().year
+            metadata_options.extend(["-metadata", f"date={current_year}"])
+
+        # Add album artist metadata
+        if album_artist_match:
+            metadata_options.extend(["-metadata", f"album_artist={album_artist_match.group(1)}"])
+        else:
+            metadata_options.extend(["-metadata", f"album_artist=Unknown"])
+            
+        # Add these to ffmpeg command
+        return metadata_options
+
     def _srt_time(self, t):
         """Helper function to format time for SRT files"""
         h = int(t // 3600)

abogen/gui.py

@@ -938,10 +938,12 @@ class abogen(QWidget):
                             title = re.sub(r'<[^>]+>', '', str(dialog.book_metadata.get('title', 'Unknown')))
                             publisher = re.sub(r'<[^>]+>', '', str(dialog.book_metadata.get('publisher', 'Unknown')))
                             authors = [re.sub(r'<[^>]+>', '', str(author)) for author in dialog.book_metadata.get('authors', ['Unknown'])]
+                            publication_year = re.sub(r'<[^>]+>', '', str(dialog.book_metadata.get('publication_year', 'Unknown')))
                             
                             f.write(f"Title: {title}\n")
                             f.write(f"Authors: {', '.join(authors)}\n")
                             f.write(f"Publisher: {publisher}\n")
+                            f.write(f"Publication Year: {publication_year}\n")
                             if dialog.book_metadata.get('description'):
                                 description = re.sub(r'<[^>]+>', '', str(dialog.book_metadata.get('description')))
                                 f.write(f"\nDescription:\n{description}\n")